A new model to forecast energy inflation in the euro area

Marta Bańbura, Elena Bobeica, Alessandro Giammaria, Mario Porqueddu and Josha van Spronsen

No 3062, Working Paper Series from European Central Bank

Abstract: Energy inflation is a major source of headline inflation volatility and forecast errors, therefore it is critical to model it accurately. This paper introduces a novel suite of Bayesian VAR models for euro area HICP energy inflation, which adopts a granular, bottom-up approach – disaggregating energy into subcomponents, such as fuels, gas, and electricity. The suite incorporates key features for energy prices: stochastic volatility, outlier correction, high-frequency indicators, and pre-tax price modelling. These characteristics enhance both in-sample explanatory power and forecast accuracy. Compared to standard benchmarks and official projections, our BVARs achieve better forecasting performance, particularly beyond the very short term. The suite also captures a sizable variation in the impact of commodity price shocks, pointing to higher elasticities at higher levels of commodity prices. Beyond forecasting, our framework is also useful for scenario and sensitivity analysis as an effective tool to gauge risks, which is especially relevant amid ongoing energy market transformations. JEL Classification: C32, C53, E31, E37

Keywords: Bayesian VAR; gas prices; HICP; oil prices (search for similar items in EconPapers)
Date: 2025-06
Note: 810771
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.ecb.europa.eu//pub/pdf/scpwps/ecb.wp3062~abe560353f.en.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ecb:ecbwps:20253062

Access Statistics for this paper

More papers in Working Paper Series from European Central Bank 60640 Frankfurt am Main, Germany. Contact information at EDIRC.
Bibliographic data for series maintained by Official Publications ().